Guest Editors
Prof. Celimuge Wu
Email: celimuge@uec.ac.jp
Affiliation: Meta-Networking Research Center, The University of Electro-Communication, Tokyo, Japan
Homepage:
Research Interests: IoT, AI, edge computing
Prof. Soufiene Djahel
Email: ae3095@coventry.ac.uk
Affiliation: Centre for Future Transport and Cities, Coventry University, Coventry, United Kingdom
Homepage:
Research Interests: wireless networks, cyber security, intelligent transportation systems (ITS), smart cities
Assoc. Prof. Jie Feng
Email: fengjie@xidian.edu.cn
Affiliation: School of Telecommunications Engineering, Xidian University, Xi'an, China
Homepage:
Research Interests: wireless networks, edge computing, cyber security
Prof. Kok-Lim Alvin Yau
Email: yaukl@utar.edu.my
Affiliation: Lee Kong Chian Faculty of Engineering and Science, Universiti Tunku Abdul Rahman, Kajang, Malaysia
Homepage:
Research Interests: applied reinforcement learning, applied artificial intelligence, augmented intelligence, wireless networking
Dr. Zhaoyang Du
Email: duzhaoyang@uec.ac.jp
Affiliation: Department of Computer and Network Engineering, The University of Electro-Communication, Tokyo, Japan
Homepage:
Research Interests: IoT, AI, machine learning, wireless networking
Summary
As distributed systems and machine learning increasingly rely on massive data collection, the shift toward decentralized networks exposes sensitive information to broader security risks. With stringent global regulations, privacy computing becomes a fundamental requirement, yet balancing privacy guarantees, model utility, and system efficiency remains a core technical challenge. While differential privacy offers rigorous mathematical protections, optimizing its deployment in complex settings requires extensive research. Consequently, integrating robust privacy mechanisms into Machine Learning, Edge Intelligence, and Semantic Communications is imperative for securing diverse infrastructures. These target environments range from Low-Power Wide-Area Networks and vehicular systems to comprehensive Space-Air-Ground Integrated Networks.
This Special Issue invites original research and comprehensive review articles addressing privacy challenges in intelligent systems. A key objective is to highlight the synergy between privacy algorithms and advanced networking architectures, including intelligent network management and wireless localization. Topics of interest include, but are not limited to:
· Theoretical foundations and advanced mechanisms of Differential Privacy
· Privacy-preserving Federated Learning and its system-level optimizations
· Privacy-preserving Semantic Communication for vehicular and intelligent networks
· Privacy-aware Edge Computing and decentralized AI architectures
· Trade-offs between privacy guarantees, model utility, and communication efficiency
· Secure Multi-party Computation and Homomorphic Encryption in distributed systems
· Privacy-preserving integration for 6G and Space-Air-Ground Integrated Networks
· Privacy and security in intelligent network management and wireless localization systems
· Robustness, vulnerability analysis, and defense mechanisms for privacy-preserving models
· Hardware acceleration and experimental testbeds for privacy computing
· Trustworthy, explainable, and neuro-symbolic AI in privacy-sensitive domains
Keywords
differential privacy; privacy computing; federated learning; semantic communications; distributed intelligence; edge computing; V2X communications
Login
Register
Submit a Paper
Propose a Special lssue